Coastal landscape classification using convolutional neural network and remote sensing data in Vietnam.

The length of global coastline is about 356 thousand kilometers with various dynamic natural and anthropogenic. Although the number of studies on coastal landscape categorization has been increasing, it is still difficult to distinguish precisely them because the used methods commonly are traditional qualitative ones. With the leverage of remote sensing data and GIS tools, it helps categorize and identify a variety of features on land and water based on multi-source data. The aim of study is using different natural - social profile data obtained from ALOS, NOAA, and multi-temporal Landsat satellite images as input data of the convolutional-neural-network (CvNet) models for coastal landscape classification. Studies used 900 cut-line samples which represent coastal landscapes in Vietnam for training and optimizing CvNet models. As a result, nine coastal landscapes were identified including: deltas, alluvial, mature and young sand dunes, cliff, lagoon, tectonic, karst, and transitional landscapes. Three CvNet models using three different optimizer types classified the landscapes of other 1150 cut-lines in Vietnam with the accuracies about 98% and low loss function value. Excepting dalmatian, karst and delta coastal landscapes, five others distribute heterogeneous along the coasts in Vietnam. Therefore, the evaluation of additional natural components is necessary and CvNet model have ability to update new landscape types in variety of tropical nation as a step toward coastal landscape classification at both national and global scales.

Natural radionuclides and assessment of radiological hazards in MuongHum, Lao Cai, Vietnam.

226Ra, 238U, 4 K, and 232Th (228Ra) activity concentrations of 61 soil samples distributed surrounding the rare earth element mine (NORM), MH, Lao Cai, Vietnam have been measured by HPGe detector. The activity concentrations of 226Ra, 238U, 4 K, and 232Th (228Ra) range from 1179 to 6291 Bq/kg, from 1024 to 8351 Bq/kg, from 260 to 3519 Bq/kg, and from 1476 to 35546 Bq/kg in the ore body and from 21.3 to 964 Bq/kg, from 23.4 to 1635 Bq/kg, from 124 to 3788 Bq/kg, and from 40.9 to 6107 Bq/kg outside the ore body in respective. The study area is considered as the high local natural background radiation with the concentration of 226Ra, 238U, 4 K, and 232Th (228Ra) of 156, 254, 647, and 908 Bq/kg in respective. Regarding the spatial distribution, the measured radionuclide concentrations are independent of the distance from measured points to the ore body. With regard to the hazard indices, the average calculated radiological hazard indices, including absorbed gamma dose rate, effective dose equivalent, and excess lifetime cancer risk significantly exceed the global average values. There is a disequilibrium between 238U/226Ra concentrations in studied soil samples. The results also found that the 232Th (228Ra) concentration and total absorbed gamma dose rate show a strong positive correlation (coefficient of determination, R2 = 1).